深度专题
India’s MoEngage bets that the future of marketing is millions of AI agents: The all-cash deal gives MoEngage access to technology that assigns AI agents to individual customers.
查看深度信号India’s MoEngage bets that the future of marketing is millions of AI agents: The all-cash deal gives MoEngage access to technology that assigns AI agents to individual customers.
Anthropic’s Claude Tag is learning your company, one Slack message at a time: Anthropic’s new Claude Tag brings an always-on AI teammate to Slack. But beyond productivity, the feature is a strategic play to capture organizational context, institutional knowledge, and enterprise workflows.
Shipping huggingface_hub every week with AI, open tools, and a human in the loop
Bluerails Discovery: The rails AI agents use to find and pay you Discussion | Link
Blazly SEO: Dominate SEO with an AI content operating system Discussion | Link
bug(rag): query side appends /faiss_index but ingest writes to vectordb_dir directly → KB retrieval never finds the index (#1951 follow-on): ## Severity **High** — RAG retrieval is broken for the standard config path: `query_knowledge_base` returns *"no knowledge base found"* even when an index was successfully ingested. Affects any setup where ingest and que
Show HN: New AI edits images based on text instructions: This works suprisingly well. Just give it instructions like "make it winter" or "remove the cars" and the photo is altered. Here are some examples of transformations it can make: Golden gate bridge: https://raw.githubuse
Show HN: AI Dungeon 2 – AI-generated text adventure built with 1.5B param GPT-2
SPEC: gwt自己改善フィードバックループ — Improvement Inbox・自動Issue化・高確度Stop-block: # SPEC: gwt自己改善フィードバックループ — Improvement Inbox・自動Issue化・高確度Stop-block ## 背景 gwt は複数エージェントを使ってアプリケーション開発を進めるための orchestration software であり、gwt 自身の開発でもスキル、managed guidance、AGENTS.md、hook、Issue/SPEC workflow が実行品質を左右する。現在は `
Native xai-sdk Live Search broken on live endpoint — migrate from deprecated SearchParameters to xAI Agent Tools API: ## Caught by capital live-verify of #165 (v0.37.0) against the real xAI endpoint — before release The native `XaiSdkProvider` (#165) wires Live Search (the `web_search` / `x_search` opt-in built-ins) as a native `SearchP
AI Review Agents are hallucinating truncated snippets as syntax errors: ## UNDERSTAND THE ISSUE ### Problem Statement The AI Review agents are frequently hallucinating code snippets that do not actually exist in the pull request diffs, leading them to falsely flag "syntax errors" or other bl
OpenCode – Open source AI coding agent
AlphaEvolve: A Gemini-powered coding agent for designing advanced algorithms: See also https://www.nature.com/articles/d41586-025-01523-z ( https://archive.is/NBaXE )
DeepSeek reasonix, DeepSeek native coding agent with high caching and low cost: Related ongoing thread: DeepSeek makes the V4 Pro price discount permanent - https://news.ycombinator.com/item?id=48237663 - May 2026 (384 comments)
SnapState - Persistent state for AI agent workflows
Show HN: Elf0 – Build and run AI agent workflows in YAML (CLI): Hi HN — I built Elf0, a command-line tool to define and run AI agent workflows in YAML. It helps you iterate on small multi-step "agents" without scaffolding a whole codebase. The agent patterns described in Anthropic's
Show HN: A GitOps-style registry for AI agent Workflows, Skills and MCP servers
Unlocking UK house-building with AI-accelerated planning: UK government partners with Google DeepMind to build a new AI-powered prototype aimed at faster housing decisions.
Securing the future of AI agents: Securing internal systems with an AI Control Roadmap, combining traditional safeguards and real-time monitoring.
Investing in multi-agent AI safety research: Google DeepMind and partners announce a $10M funding call for multi-agent safety research.
Fluid, natural voice translation with Gemini 3.5 Live Translate: Gemini 3.5 Live Translate brings near real-time, natural speech translation to Google AI Studio, Google Translate and Google Meet.
Introducing LangSmith’s No Code Agent Builder: Build AI agents without code using LangSmith Agent Builder. Create agents with memory, guided prompts, and MCP tools—no technical expertise needed.
The Art of Loop Engineering: Agents automate real-world work, but reliable performance requires more than a good model, it requires a carefully designed harness built for specific tasks. This post explores the core agent loop, how stacking and exten
Designing Efficient Verifiers for Legal Agents: A Harvey and LangChain Labs study on making LLM verifiers cheaper and more reliable for legal-agent evaluation and post-training.
4 paths to Frontier Transformation: From AI experimentation to real business value: AI is moving from experimentation to enterprise impact, with leading organizations focusing on four key paths to unlock business value across employees, customers, operations, and innovation. By embedding AI into workflo
Achieving success with AI: The two most important elements in any AI solution are intelligence and trust. I first made this statement in November at our Ignite conference and my conviction is strengthened by every conversation I have with customer
Scaling AI with 8 to 20x energy efficiency: As AI becomes part of daily life for people and organizations around the world, that shift brings a responsibility to understand—and minimize—its environmental impact. That responsibility is especially real in the commun
The CMO on the frontier: From AI experimentation to AI at work: Marketing is at an inflection point. Across industries, CMOs are no longer asking whether AI will transform marketing but how fast they can move from experimentation to impact, and how to re‑architect work so AI shows up
AI amplifies creativity by removing friction: As generative AI becomes more accessible across the enterprise, a familiar tension is emerging—especially for teams responsible for brand, storytelling, and trust. The post AI amplifies creativity by removing friction ap
New research shows how AMIE, our medical AI, could help manage health conditions.: Research in “Nature” shows our conversational AI system matches primary care physicians in complex disease management.
We’re strengthening our presence in Alabama through new investments and community support.: Google has announced a $1.5 billion investment for 2026 and 2027 to expand its data center campus in Jackson County, Alabama. Operating since 2019 on a repurposed former…
Our new community investments in Virginia support local jobs and expand energy affordability.: We’re helping build the state’s next-generation workforce and investing in energy programs.
The latest AI news we announced in May 2026: Here are Google’s latest AI updates from May 2026
5 ways Google Search can level up your thrift and vintage shopping: Uncover second-hand scores with AI tools in Google Search and Shopping.
Helping build shared standards for advanced AI: OpenAI helps build shared standards for advanced AI, supporting evaluation frameworks, safety practices, and global cooperation through the Appia Foundation.
How GPT-5 helped immunologist Derya Unutmaz solve a 3-year-old mystery: GPT-5 Pro helped solve a 3-year-old immunology mystery, offering insights into T cell behavior. The breakthrough could support cancer and autoimmune research.
How Omio is building the future of conversational travel: Discover how Omio uses OpenAI to power conversational travel experiences, accelerate product development, and transform into an AI-native company.
Patch the Planet: a Daybreak initiative to support open source maintainers: OpenAI introduces Patch the Planet, a Daybreak initiative helping open-source maintainers find, validate, and fix vulnerabilities with AI and expert review.
Fika Jobs raises $4M to build a video-first hiring platform where AI agents interview candidates: Stockholm-based startup Fika Jobs is building a video-first hiring platform that combines AI interview agents with short-form video profiles, creating something that feels like a cross between LinkedIn and TikTok.
The running list: major tech layoffs in 2026 where employers cited AI: A running look — in reverse chronological order — at the bigger tech companies that have announced significant layoffs this year with AI as a stated factor.
Tencent EdgeOne Makers: Ship AI agents like web apps, in minutes. Discussion | Link
Propane: Automatic customer context for product teams and agents. Discussion | Link
Customer Relationship Agents by Clarify: The M in CRM shouldn't be you Discussion | Link
[Bug]: Title: GAMOptSettings.random_state is unused — GAM exploration is non-deterministic: ### Bug Description # GAMOptSettings.random_state is unused — GAM exploration order is non-deterministic ## Summary `GAMOptSettings` exposes `random_state` (default `64`), but `GAMOptimizer` never uses it. Initial hyperp
👋 Hello! Introducing myself: ## Hi everyone! 👋 I'm **Claude Code**, Anthropic's official CLI assistant, here to lend a hand on the **buster-project**. ### Who I am - 🤖 An AI coding agent working through the `busterbunny69` account - 🛠️ I help with s
[BUG] [Knowledge Base] - NIST 800-53 catalog search returns empty results for all queries including well-known controls (AC-2, 'access control', 'access'): ## Bug Description The NIST 800-53 knowledge base tools (`kb_search_nist_controls`, `kb_explain_nist_control`, `search_nist_controls`) return empty results or "catalog entry not found" for all queries — even well-known c
[Bug]: resolve skill bundles times out: full bundle re-downloaded on every task dispatch (no cache), fails on slow links: ## Summary When an agent has more than a handful of skills bound, **every task dispatched to it fails before the agent even starts**, with: ``` resolve skill bundles: context deadline exceeded (Client.Timeout or context
Add top-level CLI error handling with defined exit codes and stderr discipline: ## Summary Catch expected failure classes (`ValueError` from validation, `FileNotFoundError` for inputs, permission errors for outputs) in `cli.py::main`, print concise messages to stderr, and exit with documented codes
feat(skills): add prose-self-check skill — 4-layer AI-vernacular audit before agents emit prose artifacts: ## Context Agents in this repo emit long prose artifacts (session-log narratives, ADR context sections, retrospectives, PR descriptions). The repo enforces **code** quality (CodeQL, complexity, coverage), **structural**
Show HN: Air Lab – A portable and open air quality measuring device: Hi HN! I’ve been working on an air quality measuring device called Air Lab for the past three years. It measures CO2, temperature, relative humidity, air pollutants (VOC, NOx), and atmospheric pressure. You can log and a
Show HN: LLM-aided OCR – Correcting Tesseract OCR errors with LLMs: Almost exactly 1 year ago, I submitted something to HN about using Llama2 (which had just come out) to improve the output of Tesseract OCR by correcting obvious OCR errors [0]. That was exciting at the time because OpenA
Zerostack – A Unix-inspired coding agent written in pure Rust
Worktrunk: Git worktree management for parallel AI agent workflows
Orca – Executable skills and capabilities for AI agent workflows
Crewdle AI: Use every business AI tool without every subscription Discussion | Link
Swimio: AI swim coach with Apple Watch tracking & smart workouts Discussion | Link
[QA Bug] REG-003 — Category and gender filters narrow the catalog: # 🐞 Category and gender filters narrow the catalog **Test:** `REG-003` · **Priority:** P2 · **Features:** catalog, filters **Run:** [Daily regression · ShoeStore · run 8](https://hyperexecute.lambdatest.com/hyperexecute/
Systematic Exploration of 4-Expert Heterogeneous Mixture-of-Experts via Automated Pipeline Search: arXiv:2606.23739v1 Announce Type: new Abstract: We present an automated large-scale search pipeline for heterogeneous 4-Expert Mixture-of-Experts (MoE4) architectures within the LEMUR neural network dataset ecosystem. Bu